02/02/2021

Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain

Jinyu Tian, Jiantao Zhou, Yuanman Li, Jia Duan

Keywords:

Abstract Paper Similar Papers

Abstract: Deep neural networks (DNNs) have been shown to be vulnerable against adversarial examples (AEs), which are maliciously designed to cause dramatic model output errors. In this work, we reveal that normal examples (NEs) are insensitive to the fluctuations occurring at the highly-curved region of the decision boundary, while AEs typically designed over one single domain (mostly spatial domain) exhibit exorbitant sensitivity on such fluctuations. This phenomenon motivates us to design another classifier (called dual classifier) with transformed decision boundary, which can be collaboratively used with the original classifier (called primal classifier) to detect AEs, by virtue of the sensitivity inconsistency. When comparing with the state-of-the-art algorithms based on Local Intrinsic Dimensionality (LID), Mahalanobis Distance (MD), and Feature Squeezing (FS), our proposed Sensitivity Inconsistency Detector (SID) achieves improved AE detection performance and superior generalization capabilities, especially in the challenging cases where the adversarial perturbation levels are small. Intensive experimental results on ResNet and VGG validate the superiority of the proposed SID.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948184
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 14:30 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 5:04 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 14:46 
 0
 1
 0
 0
 11:09 
 0
 0
 0
 0
 14:54 
 0
 0
 0
 0
 11:21 
 0
 0
 0
 0
 5:20 
 0
 0
 0
 0
 14:51 
 0
 0
 0
 0
 9:28 
 0
 0
 0
 0
 4:30 
 0
 0
 0
 0
 4:47 
 0
 0
 0
 1
 3:14 
 0
 0
 0
 0
 15:12 
 0
 0
 0
 0
 8:21 
 0
 0
 0
 0
 16:00 
 0
 0
 0
 0
 15:16 
 0
 0
 0
 0
 10:00 
 0
 0
 0
 0
 13:40 
 0
 0
 0
 0
 5:19 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 10:28 
 0
 0
 0
 0
 5:22 
 0
 0
 0
 0
 7:48 
 0
 0
 0
 0
 10:56 
 0
 0
 0
 0
 14:43 
 0
 0
 0
 0
 14:21 
 0
 0
 0
 0
 15:08 
 1
 0
 0
 0
 5:11 
 0
 0
 0
 0
 12:48 
 0
 0
 0
 0
 3:27 
 0
 0
 0
 0
 12:40 
 0
 0
 0
 0
 13:34 
 0
 0
 0
 0
 13:33 
 0
 0
 0
 0
 15:06 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 1:00